6 papers
Witness Overlap: Directional Provenance Inside Open-Weight Model Families
Siyuan Li, Haoxuan Zeng, Xin Luo +6
Open-weight models are often released, fine-tuned, aligned, merged, and re-released, making provenance audits ask not only whether checkpoints are related, but also which checkpoin…
VOICE: A Vision-Omics Foundation Model Integrating Direct and Retrieval-Based Prediction of In-situ Single-Cell Gene Expression
Xin Luo, Yicheng Tao, Haoxuan Zeng +6
Spatial transcriptomics can resolve gene expression at single-cell resolution, but it is costly, limited to targeted panels of a few hundred to a few thousand genes, and applicable…
GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases
Yicheng Tao, Yiqun Wang, Xiangchen Song +4
Retrieval over semi-structured knowledge bases (SKBs) must handle both textual descriptions and relational constraints. Text-based retrievers capture the overall semantics of a que…
The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
Jiayuan Liu, Tianqin Li, Shiyi Du +7
Context window expansion is often treated as a straightforward capability upgrade for LLMs, but we find it systematically fails in multi-agent social dilemmas. Across 7 LLMs and 4…
Quantized-Tinyllava: a new multimodal foundation model enables efficient split learning
Jiajun Guo, Xin Luo, Jiayin Zheng +4
Multimodal foundation models are increasingly trained on sensitive data across domains such as finance, biomedicine, and personal identifiers. However, this distributed setup raise…
AutoPCR: Automated Phenotype Concept Recognition by Prompting
Yicheng Tao, Yuanhao Huang, Yiqun Wang +2
Motivation: Phenotype concept recognition (CR) is a fundamental task in biomedical text mining. However, existing methods either require ontology-specific training, making them str…